The production environment of greenhouse cultivation is relatively closed,the multiple cropping index is high,the management of fertilizationwatering and pesticideapplication isblindtosomeextent,andthe phenomenonofcon...The production environment of greenhouse cultivation is relatively closed,the multiple cropping index is high,the management of fertilizationwatering and pesticideapplication isblindtosomeextent,andthe phenomenonofcontinuous cropping isalsocommonSoilquali-ty affects the sustainable development of greenhouse cultivation.Earthworm is a ubiquitous invertebrate organism in soil,an important part of soil system,a link between terrestrial organisms and soil organisms,an important link in the small cycle of soil material organisms,and plays an important role in maintaining the structure and function of soil ecosystem.Different ecotypes of earthworms are closely related to their habi-tats(soil layers)and food resource preferences,and then affect their ecological functions.The principle of earthworm regulating soil function is essentially the close connection and interaction between earthworm and soil microorganism.Using different ecotypes of earthworms and bio-logical agents to carry out combined remediation of greenhouse cultivation soil is a technical model to realize sustainable development of green-house cultivation.展开更多
The increasing Uganda’s urban population growth has led to limited space coupled with high cost of living, thus making it difficult for the urban poor in congested areas to afford fish protein hence poor nutrition am...The increasing Uganda’s urban population growth has led to limited space coupled with high cost of living, thus making it difficult for the urban poor in congested areas to afford fish protein hence poor nutrition among the low income earners. Therefore this study was conducted to evaluate the performance of collard based bio-filtration system for filtering fish tank effluent for re-use in congested peri-urban areas. Field physical-chemical parameters (ammonia, nitrate, dissolved oxygen, temperature and pH) were measured at various bio-filter lengths in the effluent from both collard based and GBF (Gravel Based Bio-Filter). Differences in mean ammonia and nitrate levels at various lengths were analyzed using one-way ANOVA at p = 0.05. Ammonia levels were significantly reduced (p < 0.05) at various lengths: L0 99.1 mg/L;L1 75.8 mg/L (23.6%);L2 53.1 mg/L (46.4%);L3 25.8 mg/L (74%) and L4 6.6 mg/L (93.4%). Similarly, nitrate levels significantly reduced (p < 0.05): L0 11.8 mg/L;L1 7.2 mg/L (39.4%);L2 3.6 mg/L (69.2%);L3 1.6 mg/L (86.7%) and L4 0.1 mg/L (99.3%). Significant difference (p < 0.05) was obtained in mean ammonia and nitrate removal between collard based and gravel bio-filters. Collard based filter yielded higher ammonia and nitrate removal at L4 by 18.3% and 39.5% respectively, hence L4 is the effective length for collard based bio-filter.展开更多
Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass variations.Conventional techniques for this problem depend on ha...Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass variations.Conventional techniques for this problem depend on hand-crafted features,namely,LBP,SIFT,and HOG,along with that a classifier trained on a database of videos or images.Many execute perform well on image datasets captured in a controlled condition;however not perform well in the more challenging dataset,which has partial faces and image variation.Recently,many studies presented an endwise structure for facial expression recognition by utilizing DL methods.Therefore,this study develops an earthworm optimization with an improved SqueezeNet-based FER(EWOISN-FER)model.The presented EWOISN-FER model primarily applies the contrast-limited adaptive histogram equalization(CLAHE)technique as a pre-processing step.In addition,the improved SqueezeNet model is exploited to derive an optimal set of feature vectors,and the hyperparameter tuning process is performed by the stochastic gradient boosting(SGB)model.Finally,EWO with sparse autoencoder(SAE)is employed for the FER process,and the EWO algorithm appropriately chooses the SAE parameters.Awide-ranging experimental analysis is carried out to examine the performance of the proposed model.The experimental outcomes indicate the supremacy of the presented EWOISN-FER technique.展开更多
基金Supported by Key Scientific Research Project in Colleges and Universities of Henan Province(22B180011)Project of Henan Provincial Department of Science and Technology(232102320262)+1 种基金Education and Teaching Reform Research Project of Pingdingshan University(2021-JY55)Key Demonstration Course of Pingdingshan University in 2022——Comprehensive Experiment of Environmental Biology.
文摘The production environment of greenhouse cultivation is relatively closed,the multiple cropping index is high,the management of fertilizationwatering and pesticideapplication isblindtosomeextent,andthe phenomenonofcontinuous cropping isalsocommonSoilquali-ty affects the sustainable development of greenhouse cultivation.Earthworm is a ubiquitous invertebrate organism in soil,an important part of soil system,a link between terrestrial organisms and soil organisms,an important link in the small cycle of soil material organisms,and plays an important role in maintaining the structure and function of soil ecosystem.Different ecotypes of earthworms are closely related to their habi-tats(soil layers)and food resource preferences,and then affect their ecological functions.The principle of earthworm regulating soil function is essentially the close connection and interaction between earthworm and soil microorganism.Using different ecotypes of earthworms and bio-logical agents to carry out combined remediation of greenhouse cultivation soil is a technical model to realize sustainable development of green-house cultivation.
文摘The increasing Uganda’s urban population growth has led to limited space coupled with high cost of living, thus making it difficult for the urban poor in congested areas to afford fish protein hence poor nutrition among the low income earners. Therefore this study was conducted to evaluate the performance of collard based bio-filtration system for filtering fish tank effluent for re-use in congested peri-urban areas. Field physical-chemical parameters (ammonia, nitrate, dissolved oxygen, temperature and pH) were measured at various bio-filter lengths in the effluent from both collard based and GBF (Gravel Based Bio-Filter). Differences in mean ammonia and nitrate levels at various lengths were analyzed using one-way ANOVA at p = 0.05. Ammonia levels were significantly reduced (p < 0.05) at various lengths: L0 99.1 mg/L;L1 75.8 mg/L (23.6%);L2 53.1 mg/L (46.4%);L3 25.8 mg/L (74%) and L4 6.6 mg/L (93.4%). Similarly, nitrate levels significantly reduced (p < 0.05): L0 11.8 mg/L;L1 7.2 mg/L (39.4%);L2 3.6 mg/L (69.2%);L3 1.6 mg/L (86.7%) and L4 0.1 mg/L (99.3%). Significant difference (p < 0.05) was obtained in mean ammonia and nitrate removal between collard based and gravel bio-filters. Collard based filter yielded higher ammonia and nitrate removal at L4 by 18.3% and 39.5% respectively, hence L4 is the effective length for collard based bio-filter.
文摘Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass variations.Conventional techniques for this problem depend on hand-crafted features,namely,LBP,SIFT,and HOG,along with that a classifier trained on a database of videos or images.Many execute perform well on image datasets captured in a controlled condition;however not perform well in the more challenging dataset,which has partial faces and image variation.Recently,many studies presented an endwise structure for facial expression recognition by utilizing DL methods.Therefore,this study develops an earthworm optimization with an improved SqueezeNet-based FER(EWOISN-FER)model.The presented EWOISN-FER model primarily applies the contrast-limited adaptive histogram equalization(CLAHE)technique as a pre-processing step.In addition,the improved SqueezeNet model is exploited to derive an optimal set of feature vectors,and the hyperparameter tuning process is performed by the stochastic gradient boosting(SGB)model.Finally,EWO with sparse autoencoder(SAE)is employed for the FER process,and the EWO algorithm appropriately chooses the SAE parameters.Awide-ranging experimental analysis is carried out to examine the performance of the proposed model.The experimental outcomes indicate the supremacy of the presented EWOISN-FER technique.